Related papers: Agent-GSPO: Communication-Efficient Multi-Agent Sy…

Inter-agent communication can significantly increase performance in multi-agent tasks that require co-ordination to achieve a shared goal. Prior work has shown that it is possible to learn inter-agent communication protocols using…

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often…

This work considers the problem of learning cooperative policies in multi-agent settings with partially observable and non-stationary environments without a communication channel. We focus on improving information sharing between agents and…

Adversarial optimization algorithms that explicitly search for flaws in agents' policies have been successfully applied to finding robust and diverse policies in multi-agent settings. However, the success of adversarial optimization has…

Multi-agent systems (MAS) based on large language models (LLMs) have demonstrated significant potential in collaborative problem-solving. However, they still face substantial challenges of low communication efficiency and suboptimal task…

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, Chain-of-Thought with…

Hybrid training methods for large language models combine supervised fine tuning (SFT) on expert demonstrations with reinforcement learning (RL) on model rollouts, typically at the sample level. We propose Entropy Gated Selective Policy…

Group-Relative Policy Optimization (GRPO) is a key technique for training large reasoning models, yet it suffers from a critical vulnerability: the \emph{Think-Answer Mismatch}, where noisy reward signals corrupt the learning process. This…

While Visual Multi-Agent Systems (VMAS) promise to enhance comprehensive abilities through inter-agent collaboration, empirical evidence reveals a counter-intuitive "scaling wall": increasing agent turns often degrades performance while…

The rapid evolution of Large Language Models (LLMs) has accelerated the transition from conversational chatbots to general agents. However, effectively balancing empathetic communication with budget-aware decision-making remains an open…

Finding optimal adversarial attack strategies is an important topic in reinforcement learning and the Markov decision process. Previous studies usually assume one all-knowing coordinator (attacker) for whom attacking different recipient…

A multi-agent AI system (MAS) is composed of multiple autonomous agents that interact, exchange information, and make decisions based on internal generative models. Recent advances in large language models and tool-using agents have made…

Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks. Existing implementations typically rely on a single agent, but they suffer from limited context…

The teleoperated driving (TD) scenario comes with stringent Quality of Service (QoS) communication constraints, especially in terms of end-to-end (E2E) latency and reliability. In this context, Predictive Quality of Service (PQoS), possibly…

In multi-agent applications such as surveillance and logistics, fleets of mobile agents are often expected to coordinate and safely visit a large number of goal locations as efficiently as possible. The multi-agent planning problem in these…

We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a review of the…

This paper proposes a GRPO-based approach to enhance the performance of large language model (LLM)-based text-to-speech (TTS) models by deriving rewards from an off-the-shelf automatic speech recognition (ASR) model. Compared to previous…

Group Relative Policy Optimization (GRPO) has emerged as a promising approach for improving the reasoning capabilities of large language models. However, it struggles to effectively balance the tradeoff between exploration and exploitation…

Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation,…

Multi-agent networked linear dynamic systems have attracted attention of researchers in power systems, intelligent transportation, and industrial automation. The agents might cooperatively optimize a global performance objective, resulting…